© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2642
    Prev
    Next
    INDEX
    Explanations

    renormalization theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıĮåŁİ
    -0.08
    undles
    -0.08
     strugg
    -0.08
    çݺ
    -0.08
    vro
    -0.08
    uffled
    -0.08
    åıĮèĥŀèĥİ
    -0.07
     billets
    -0.07
    åĽ½å¼º
    -0.07
    ç«Ńè¯ļ
    -0.07
    POSITIVE LOGITS
     limit
    0.07
    åıįå¤į
    0.06
    éľĢè¦ģçĶ¨
    0.06
    æ¼ıæ´ŀ
    0.06
    á»ģ
    0.06
    à¸Ńุà¸Ķ
    0.06
    å¤Ń
    0.06
    æģ¶åĮĸ
    0.06
    ugen
    0.06
    uges
    0.06
    Activations Density 0.004%

    No Known Activations